2026 Study Goal: Machine Learning Fundamentals
One of my main study goals for 2026 is to gain a deeper understanding of Machine Learning. It was previously a sub-discipline of AI, but has become synonymous with it as its been the impetus in the latest breakthroughs like ChatGPT.
I. Training Setup
You actually don't really need a powerful laptop. I'm doing okay thus far on an ancient 6th gen Intel i7 laptop and its doing quite well and when I hit the more compute intensive I'll sign up for Google Colab to leverage cloud compute.
- Computer
- HP ab292nr - Intel i7-6700HQ
- 16 gb RAM
- 1 tb SSD
- Software
- VS Code - Code Editor/IDE
- Notepad++
- Python {scikit-learn, numpy, pandas, matplotlib, torch, streamlit}
- Github
- Docker
- Streamlit.io
- Vibe Coding
- ChatGPT
- Claude
II. ChatGPT
I'm leveraging ChatGPT for vibe coding and looking up definitions, terms and validating concepts from my training. It is also one of the first things most people consider as AI.
III. Online ML Courses - Introduction
I’m starting with the Google Machine Learning Crash Course as my December 2025 study focus, followed by a more structured MOOC such as an edX Machine Learning course. I’ve found that learning terminology is especially important—knowing that “stochastic” means random or that a “token” represents a word makes abstract concepts far easier to grasp.
Self-Study 1.5 hrs --> 35 hrs
To make meaningful progress, I’m increasing my study time from 1–2 hours per week to about 30-40 hours per week, roughly 5 hours a day. By January 2026, my goal is to complete the Google course, internalize the glossary, and clearly understand the core concepts.
IV. Fundamentals - Math
Next would be to brush up on my Math. It's been a while since I last took Calculus in College, so I'm hoping its not too difficult to pick up again. Considering the 12-week Coursera Math for ML and DS specialization.
V. Statistics
VI. Python ML Projects
Along the way, I’ll experiment in Python, starting with simple ML projects like email spam detection. My focus is on building strong fundamentals—knowledge that will remain valuable even as tools and trends continue to evolve.
I'll start with Scikit-Learn, PyTorch:
- O’Reilly - Hands On Machine Learning with Scikit, PyTorch
VII. MLOps + ML systems (Docker / Streamlit.io)
VIII. Learning Plan & Schedule
- 12/15/25 ~ 1/21/26 - 6 weeks
- Google ML Vocabulary - done 1/11/26
- Google ML Crash Course - done 1/21/26
- 1/22/26 ~ 4/19/26 - 12 weeks
- Statistics 110
- HOMLP
- Scikit, PyTorch ML Model Build
- Docker App
- Streamlit.io App
- 4/20 ~ 7/12/26 - 12 weeks
- Coursera - Math for ML/DS
- Scikit, PyTorch ML Model Build

Comments
Post a Comment